© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18458
    Prev
    Next
    INDEX
    Explanations

    template typename syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     graphene
    0.47
    тное
    0.39
    =',')
    0.39
     hInstance
    0.38
    )<-
    0.37
     starving
    0.36
     horrendous
    0.36
     horrific
    0.36
    raphene
    0.36
    роме
    0.35
    POSITIVE LOGITS
    Net
    0.39
     диапа
    0.39
     Nett
    0.37
     Net
    0.35
    ppet
    0.35
    云
    0.34
    Miller
    0.34
    Finder
    0.34
    System
    0.34
    Grund
    0.34
    Activations Density 0.006%

    No Known Activations